Shinzo MCP server

A Model Context Protocol server for managing AI agent lifecycles and observability through the Shinzo platform.

Shinzo MCP server is the control plane for your AI agent fleets: it lets models interface directly with the Shinzo platform to manage lifecycles and observability. It uses the Model Context Protocol (MCP) to provide tools for monitoring telemetry, adjusting configurations, and deploying new instances. This creates a closed-loop system where agents (like Claude) analyze their own performance metrics (like tool error rates and token costs) to autonomously refine efficiency. It leverages OpenTelemetry to track tool calls and resource usage with high precision, keeping your agentic workflows transparent and scalable.

https://github.com/shinzo-labs/shinzo-mcp